引導式測驗 · 中等 等級
對抗性例子和穩健性測驗
測試您對對抗性範例、攻擊者知識、威脅模型、訓練防禦和範圍穩健性評估的理解。
問題 1 的 8
Under a specified threat model, what is an adversarial example?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- Under a specified threat model, what is an adversarial example?
- An input crafted to cause a model error using changes allowed by that threat model
- Any ordinary prediction error on unmodified input
- An input that must contain tiny, imperceptible pixel changes
- A model update that improves accuracy on every distribution
- 「白盒」攻擊與「黑盒」攻擊有何不同?
- 白盒攻擊僅適用於白色影像
- 在白盒中,攻擊者可以存取模型的內部/梯度;在黑盒中,僅輸出
- 黑盒攻擊總是更快
- 白盒攻擊不需要計算
- FGSM(快速梯度符號法)透過...製作了一個對抗性範例
- 隨機打亂像素
- 從頭開始重新訓練模型
- 相對於輸入,沿著損失梯度的符號方向邁出一步
- 裁切影像
- What is adversarial training commonly used for?
- Guaranteeing robustness to every possible attack
- Proving a classifier is fair
- Eliminating all clean-data errors
- Improving robustness against the adversarial threat model represented during training
- 為什麼對抗性例子的「可轉移性」值得關注?
- 針對一種模型的攻擊通常會愚弄其他模型,從而實現黑盒攻擊
- 它使模型訓練速度變慢
- 它增加了儲存成本
- 它僅影響音訊模型
- How are prompt-injection attacks related to image adversarial examples?
- They are identical bounded pixel perturbations
- Both exploit model vulnerabilities, but prompt injection has a distinct instruction and system threat model
- Prompt injection requires changing model weights
- Image adversarial examples only affect text prompts
- Why must an adversarial-robustness report specify the perturbation norm and budget?
- They determine the model’s number of parameters
- They guarantee transfer to every attack
- They define which input changes the reported robustness claim covers
- They replace the need to state an attacker’s access
- Which pair of measures helps distinguish clean performance from performance under a specified attack?
- Training-set size and GPU memory
- Tokenization rate and context length
- Model file size and parameter dtype
- Clean accuracy and robust accuracy under the stated attack setting